Training in progress, step 155, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2279800052180e2d0b5e16c9e3573cfd6e5f4c4ce406192c7710c945bfa8505e
+oid sha256:4ba6ee335784d68c4888e829b763cd60225fd41fe9ee8b3e385d2f3dd5934aa4
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c84c2341f7f2a2661148030650c8ba070c72748db8ac9851a87353728776b32
+oid sha256:707aaaf6e2df60040d9e00e3db9a00d47813e4295706ec738a36dd567c30de3e
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:073c4e2f7f984e9461a9faa893b1d47e6c04d3c96899a179299dcc2a7a485197
+oid sha256:ec09fe1f5344433e3e7157913cf0a5acd5f6486a4ea5ec04487e32bab7ea3383
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e6341fe194ab0ba1103d5b0125fec96a1dce83e4ff760a1d2b649c28961287
+oid sha256:b4ae5d65e0abc18636ce4474f1a06b8abf383b8f3967693c8bd887d07e8dfd5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19411193788417988,
+  "epoch": 0.20058233581365253,
   "eval_steps": 386,
-  "global_step": 150,
+  "global_step": 155,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1065,6 +1065,41 @@
       "learning_rate": 9.983011942509131e-05,
       "loss": 1.0568,
       "step": 150
+    },
+    {
+      "epoch": 0.1954060174700744,
+      "grad_norm": 0.8052242398262024,
+      "learning_rate": 9.98267067993137e-05,
+      "loss": 0.8235,
+      "step": 151
+    },
+    {
+      "epoch": 0.19670009705596894,
+      "grad_norm": 0.9700384140014648,
+      "learning_rate": 9.982326029598931e-05,
+      "loss": 0.8611,
+      "step": 152
+    },
+    {
+      "epoch": 0.19799417664186347,
+      "grad_norm": 0.8437764048576355,
+      "learning_rate": 9.981977991746142e-05,
+      "loss": 0.83,
+      "step": 153
+    },
+    {
+      "epoch": 0.199288256227758,
+      "grad_norm": 0.930636465549469,
+      "learning_rate": 9.98162656660964e-05,
+      "loss": 1.0892,
+      "step": 154
+    },
+    {
+      "epoch": 0.20058233581365253,
+      "grad_norm": 0.9111954569816589,
+      "learning_rate": 9.98127175442836e-05,
+      "loss": 0.9962,
+      "step": 155
     }
   ],
   "logging_steps": 1,
@@ -1084,7 +1119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.676905757540352e+17,
+  "total_flos": 1.7328026161250304e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null